Naive Bayes is a probabilistic classification algorithm grounded in Bayes' theorem that assumes conditional independence among input features given the class label, enabling it to estimate the posterior probability of each class and assign the most likely label to an observation. In the context of Wi-Fi and CSI-based sensing, it serves as a lightweight, computationally efficient baseline for tasks such as indoor localization and activity recognition, where it classifies received signal measurements or fingerprints by learning per-class feature distributions from labeled training data. Common variants include Gaussian Naive Bayes, which models continuous features as normally distributed, and multinomial or Bernoulli forms suited to discrete or binary inputs; its memoryless nature — requiring no retention of individual training samples at inference time — makes it particularly attractive for resource-constrained IoT deployments where low latency and minimal memory overhead are priorities.
Source Papers
- A survey on CSI-based Wi-Fi sensing datasets and models with a focus on reproducibility ↗ — A survey on CSI-based Wi-Fi sensing datasets and models with
- Channel State Information from Pure Communication to Sense and Track Human Motion: A Survey ↗ — Channel State Information from Pure Communication to Sense a
- CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing ↗ — CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing
- Memoryless Techniques and Wireless Technologies for Indoor Localization With the Internet of Things ↗ — Memoryless Techniques and Wireless Technologies for Indoor L
- Occupancy Prediction in IoT-Enabled Smart Buildings: Technologies, Methods, and Future Directions ↗ — Occupancy Prediction in IoT-Enabled Smart Buildings: Technol
- WiFi Sensing with Channel State Information ↗ — WiFi Sensing with Channel State Information